© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 6896
    Prev
    Next
    INDEX
    Explanations

    mentions of the Academy or Academy Awards

    oai_token-act-pair · gpt-3.5-turbo

    references to various academies in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meier
    -0.74
    ppings
    -0.72
    sheet
    -0.72
    TPS
    -0.69
    pd
    -0.66
    sheets
    -0.66
    bare
    -0.65
    nir
    -0.65
    bring
    -0.64
     subsistence
    -0.64
    POSITIVE LOGITS
     Awards
    1.01
    emies
    0.94
     Academy
    0.94
     Award
    0.80
    Grade
    0.79
    æ©
    0.78
     Ruins
    0.78
    rats
    0.78
    alon
    0.72
    ritic
    0.70
    Activations Density 0.008%

    No Known Activations